Index Codes for Multibiometric Pattern Retrieval

Abstract

Abstract-In a biometric identification system, the identity corresponding to the input data (probe) is typically determined by comparing it against the templates of all identities in a database (gallery). Exhaustive matching against a large number of identities increases the response time of the system and may also reduce the accuracy of identification. One way to reduce the response time is by designing biometric templates that allow for rapid matching, as in the case of IrisCodes. An alternative approach is to limit the number of identities against which matching is performed based on criteria that are fast to evaluate. We propose a method for generating fixed-length codes for indexing biometric databases. An index code is constructed by computing match scores between a biometric image and a fixed set of reference images. Candidate identities are retrieved based on the similarity between the index code of the probe image and those of the identities in the database. The proposed technique can be easily extended to retrieve pertinent identities from multimodal databases. Experiments on a chimeric face and fingerprint bimodal database resulted in an 84% average reduction in the search space at a hit rate of 100%. These results suggest that the proposed indexing scheme has the potential to substantially reduce the response time without compromising the accuracy of identification.

Fused Index Code Based Multibiometric Pattern Retrieval Security System

“…The hit rate is the percentage of probes for which the corresponding gallery image with the correct identity is retrieved by the indexing mechanism [6] Where Nh is the number of tests in which the correct identity is present in the candidate list and N is the total number of tests. The penetration rate is the average reduction in the search space achieved by the indexing scheme.…”

Efficient Large-Scale Video Retrieval via Discriminative Signatures

“…[10]. Besides video signatures, fingerprint [15] or index codes [18] were also researched for fast matching.…”

“…[18], a set of distance scores (called index code in Ref. [18]) was generated by matching an input image against a set of reference images, and during identification, the index code was compared to the index codes of the enrolled identities. This technique led to a major improvement in computational cost, but the identification rate was usually decreased.…”

“…[18] is used to select a reference set by doing the following steps: i) the whole individual dataset is thought as a candidate pool of reference individuals; ii) for each p i , i = 1, · · · , ρ, compute mean i = Mean{s(p i , p j )} ρ j=1, j i , where s(p i , p j ) is the distance score between p i and p j ; iii) sort the individuals in descending order of their mean i and select the top N individuals as a reference set.…”

“…Since the selection of reference set has been experimentally explained in Ref. [18], we will not discuss the selection at here. For comparison, the highest mAP (N = 300) is used.…”